A tiny, fully-reproducible JEPA world model that learns the physics of a bouncing DVD logo in representation space, dreams its future, and detects anomalies. Trains on a CPU in ~10s. Interactive browser demo. CA: 0x42bef487C250dd054035d5E8d69C12549d1F7Ba3
Frozen V-JEPA 2 (300M params) + PPO policy head achieves +763 mean reward on CarRacing-v3 — 2.4x over CNN baseline, single RTX 3080
A quaternion-enhanced Video Joint-Embedding Predictive Architecture with continuous spectral autoencoders, Fourier-domain topology, and a 2D torus latent space for world model learning.
A researcher map of open-source world models - what exists, what each line of work claims, and where its authors say it breaks.
Educational implementation of V-JEPA (Video Joint Embedding Predictive Architecture) in PyTorch. Includes Conv3D tubelet embeddings, Video ViT, EMA target encoder, spatiotemporal masking, linear probing, retrieval evaluation, and effective-rank analysis on Something-Something V2.
Action-conditioned latent world model and experiment code for RoboCasa365.
To associate your repository with the v-jepa topic, visit your repo's landing page and select "manage topics."